A method for white blood cell image training set augmentation(PDF)
《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]
- Issue:
- 2023年第3期
- Page:
- 342-349
- Research Field:
- 医学影像物理
- Publishing date:
Info
- Title:
- A method for white blood cell image training set augmentation
- Author(s):
- ZANG Yu1; SU Yang2
- 1. Department of Hematology, Huizhou First Hospital, Huizhou 516000, China 2. School of Computer and Information, Dongguan City College, Dongguan 523419, China
- Keywords:
- Keywords: white blood cell identification machine learning training set augmentation
- PACS:
- R318；TP3
- DOI:
- DOI:10.3969/j.issn.1005-202X.2023.03.013
- Abstract:
- Abstract: Aiming at the low recognition accuracy of white blood cell images caused by the small training set and the need for manual intervention in the traditional method of training set augmentation, a novel method is proposed for the augmentation of the training set of white blood cell images. The edges of the black area caused by the image rotation by an arbitrary angle are extracted, and the training set augmentation is realized through filling the black area and weakening the edge features. The experimental results show that after using the training set augmented by the proposed method to train ResNet50, MobileNet and ShuffleNet, comparing with the original data set, the recognition accuracies of these models are improved by an average of 220.18%, 140.84%, 88.99%, and no manual intervention is required.
Last Update: 2023-03-29